Hugging Face's logo

Blancy
/
Qwen3-1.7B-Open-R1-GRPO

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
open-r1
trl
grpo
conversational
text-generation-inference
Model card Files
xet
Community
Blancy commited on
Commit
3608d77
·
verified ·
1 Parent(s): a3d749b

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
config.json CHANGED
@@ -24,7 +24,7 @@
24
  "tie_word_embeddings": true,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.52.3",
27
- "use_cache": true,
28
  "use_sliding_window": false,
29
  "vocab_size": 151936
30
  }
 
24
  "tie_word_embeddings": true,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.52.3",
27
+ "use_cache": false,
28
  "use_sliding_window": false,
29
  "vocab_size": 151936
30
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f736ec63abb27287a0473a3d7af8122fa79c547441b9af1df2cf377de9e8ae4
3
  size 4063515640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f6b0b4d4f78be253152850eb1d3f7d8a0be2073b7179a12f98c25f9202ba323
3
  size 4063515640
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f704f7046ab2a781b5bb9603af5b25a320beb7ae36f6a6c88d45540a1d2be93
3
  size 7928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b7c2d6ad73cb092150bb854a36699221ce7081d184c5662839df2186c97b40
3
  size 7928